Focal Interest
Focal Interest

Emotion and Mood Recognition

External reference: https://openalex.org/T10667

  1. Facial-video heart rate variability modestly distinguished depressive symptoms
    Stacking ensemble classifier combines facial video-derived heart rate variability with demographics to screen depression with moderate discrimination. AUROC 0.64 achieved across 1453 individuals.
  2. Adaptive music generation improved emotional matching
    Emotion-Conditioned Deep Reinforcement Learning framework for adaptive music generation. Achieves 98% emotion mapping accuracy with 280ms real-time responsiveness, enabling dynamic musical.